Costory: Your Finops MCP

create_virtual_dimension_draft

Create a new virtual dimension draft without publishing. virtualDimensionId in inputs equals id from list/get/search. Call get_skill with skillId: "virtual-dimensions" first — see skill for allocation shapes, CEL rules, and full workflow. For a new telemetry allocation, discover a live integration metric via list_metrics with includeExternal: true and a specific search term, then persist inline externalMetric { provider, integrationId, metricName, aggregator, groupByFields }. For BigQuery/S3, also set dateColumn and metricColumn from the returned schema (first DATE / first NUMERIC) and gapFillingMethod (default FORWARD_FILL). Catalog-complete providers (Tsuga, Datadog, CloudWatch, Amplitude, Google Cloud Monitoring) do not need those fields. Do not set datasource on new reallocations. bqName (BigQuery/CEL query field, e.g. Environment → virtual_environment) is set once from name at create and is immutable. Ordered rules use conditionCel + allocation — do not send rule id (generated on save) or values (derived). Do not include catch-all/leftover in rules — leftoverRule is auto-added. Rejects invalid payloads — nothing persisted unless validation passes. On success: virtualDimensionId, bqName, name, description, tags, values, rules with generated ids, leftoverRule, draftValidation: { ok: true }, draftPersisted: true. Use preview_virtual_dimension_draft next. Use returned bqName for groupBy/filterCel in query after publish. Does not publish or refresh BigQuery. Clerk MCP only. EXAMPLE: "Draft an Environment VDIM with a prod rule" → { name: "Environment", tagNames: ["finops"], rules: [{ name: "Production", conditionCel: "cos_environment in ["prod"]", allocation: { allocationType: "dimensionValue", dimensionValue: "prod" } }] }

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Name for the new virtual dimension
`slug`	No	Organization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
`rules`	No	Ordered rules with conditionCel and allocation
`tagNames`	No	Tag names to attach (created if missing)
`description`	No	Optional longer description (default empty).

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses key behaviors: nothing is persisted unless validation passes, bqName is immutable after creation, leftoverRule is auto-added, and the tool does not publish or refresh BigQuery. It also describes the success response shape, which is valuable because no output schema is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the tool is complex and the content is dense with operational constraints. It is front-loaded with the core purpose and provides a concrete example at the end. Some redundancy exists with the allocation schema description, but overall the length is justified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity, absence of an output schema, and rich parameter semantics, the description is remarkably complete: it covers preconditions, data discovery, validation behavior, success response fields, next steps, and post-publish usage. An agent has enough context to invoke this tool correctly and avoid common pitfalls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description goes further by explaining how parameters relate to real-world workflow: virtualDimensionId semantics, externalMetric discovery via list_metrics, required fields per provider, rule id/values being generated, and the bqName mapping. The worked example also clarifies how to structure a rules payload.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a new virtual dimension draft without publishing.' This clearly distinguishes the tool from siblings like publish_virtual_dimension, update_virtual_dimension_draft, and discard_virtual_dimension_draft. It also states the draft lifecycle constraint up front.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit workflow guidance: call get_skill first, use list_metrics with includeExternal: true for telemetry metrics, set dateColumn/metricColumn for BigQuery/S3, and use preview_virtual_dimension_draft next. It also names exclusions such as 'Do not set datasource' and 'Do not include catch-all/leftover in rules,' making the correct usage clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Costory: Your Finops MCP tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation4/5

Tools are organized by resource (alerts, dashboards, reports, events, virtual dimensions) with distinct actions, so most are clearly separable. The main confusion risks are the three report-delivery side-effect tools (run_report_now, retry_report_execution, transfer_report_execution) and the generic get that spans five resource types, though detailed descriptions mitigate these.

Naming Consistency4/5

The dominant verb_noun pattern (create_*, list_*, update_*, preview_*, get_*) is consistent and predictable across the set. Deviations like bare verbs query/search/get and the noun-only virtual_dimension_overlap_matrix are readable but break the otherwise uniform convention.

Tool Count3/5

44 tools is heavy and exceeds the comfortable range, but the server covers a genuinely broad FinOps platform spanning querying, dashboards, reports, alerts, events, virtual dimensions, docs, skills, and suggestions. Each tool has a distinct job, though the sheer count makes agent navigation harder.

Completeness3/5

Core workflows are well covered: query → dashboard/report/alert/event, plus a full virtual-dimension draft lifecycle. Notable gaps include alerts being create-only with no update/delete, no deletes for dashboards/events/published virtual dimensions, and budget management limited to query/get with no create/update.

Resources

Need Help?